Grew total data in disease models from thousands of TB to over 2.5 PB in 2 years
Improved performance and reduced costs
Cut query time from two minutes to 10 seconds
Successfully migrated its PostgreSQL databases to BigQuery, enabling it to serve over 2,000 business intelligence reports
Improved cost optimization using BigQuery’s physical billing model, Cloud Storage classes, Cloud billing export reports, quotas, and more
Keen to gain valuable insights more quickly from its data, CytoReason turned to Google Cloud to help manage the vast amounts of data at its disposal.
Since the first days of ancient medicine when physicians were prescribing leeches, humanity has been searching for the right cure. Just a few years ago, the race to find a vaccine for COVID-19 saw the world's best medical minds working with the latest technology to create vaccines that few thought would be possible to develop in such a short timeframe.
However, discovering new medicines is expensive. In the US alone, it's estimated that the cost to research and develop a single drug is $6.1 billion. The process isn't just hugely expensive, it's risky and time- consuming too. On average, it takes over ten years for a new drug to go from initial discovery to the market.
That's why many major pharmaceutical companies are looking to AI to improve efficiencies and reduce time-to-market.
Developing a new drug often means a long process of trial and error, working for years in the lab, and conducting multiple clinical trials, to get the right results. CytoReason wants to change that. The Israeli tech company creates AI-based computational disease models. With its extensive database of public and proprietary data, the company maps human diseases, tissue by tissue and cell by cell. Through its AI-led platform, CytoReason aims to help pharma companies shorten clinical trials and reduce the high costs of drug development. It's a mission that Yoav Aharoni, VP, R&D at CytoReason, was eager to be a part of. "Once I heard what CytoReason was working on, I knew that I had to be a part of it. I called them and said, 'I want in. How do I join?'"
CytoReason offers its customers a proven scientific process to gain insights and answer biological questions based on data. It has a team of scientists and data engineers who leverage the company's AI platform to pick apart and analyze huge amounts of data and get the insights that matter. For example, CytoReason has recently been working with one of its clients, Sanofi, on inflammatory bowel disease (IBD), using machine learning to help identify patient subtypes and pair them with personalized IBD targets. CytoReason's work is attracting other big pharmaceutical companies too, such as Pfizer, which wants to streamline its R&D costs, while making sure it stays on the cutting edge of AI.
"There's only so much data that humans can manually process to get the best insights. We're trying to close this gap between available data and insightful data that helps you make decisions," said Aharoni. "With Google Cloud, our teams can manage enormous amounts of data and analyze it to obtain valuable insights."
CytoReason works in multidisciplinary squads, with bioinformaticians, data scientists, engineers, DevOps, and more, on board. As the company has grown and begun working with bigger clients, it had to meet tougher deadlines. Speed is of the essence, but CytoReason was experiencing issues storing and processing its data. This was slowing down its ability to quickly get the insights it needed. The company's SQL servers could not hold all its data anymore. So the company started using BigQuery to efficiently store and query huge amounts of data at speed.
"When we switched to BigQuery we reduced the query time from two minutes to 10 seconds. That's a big difference for the guys working with the data, trying to extract insights," said Aharoni. "This means you can iterate much faster, and with certain projects this helps us to meet very strict deadlines."
CytoReason has used Google Kubernetes Engine (GKE) for some years now, but as the company expanded, it has looked at new ways to modernize its Kubernetes-based architecture without increasing significant costs. Working with Google Cloud Partner WideOps, CytoReason optimized how it uses GKE.
GKE provides CytoReason with fully automated cluster lifecycle management, pod and cluster autoscaling, cost visibility, and automated infrastructure cost optimization. The company had to be able to process lots of data quickly. So CytoReason built its own high-performance computing solution internally, which also runs on GKE.
"There are phases where we generate more disease models, which involves more processing," said Aharoni. "GKE's autoscaling takes the burden from needing to have the servers up all the time, while the health checks help ensure everything is working as it should. It means we have a highly available, scalable web application."
CytoReason's success has led Pfizer to sign a $110 million deal with the company, including a $20 million investment. CytoReason will continue to use Google Cloud to help it grow and generate advanced insights that save biotech and pharmaceutical companies money, time, and resources, as they develop next-generation therapies to change or save lives.
CytoReason is a tech company transforming biopharma’s decision-making from trial and error to data-driven using a proprietary AI Platform of computational disease models. To date, six of the world’s top ten pharma companies leverage CytoReason’s technology.
Industries: Healthcare & Life Sciences, Technology
Location: Israel
Products: Google Cloud, BigQuery, Google Kubernetes Engine , Cloud Storage
About Google Cloud Partner: WideOps
WideOps’ team of cloud experts is committed to providing solution-driven technology to help companies streamline business efficiency.